An Improved Method for Fault Diagnosis of Rolling Bearings with Optimized Parameters

Aiming at the problem that it is difficult to extract the frequency feature when the rolling bearing fails, a method of optimizing the fault feature extraction of VMD parameters by using the fruit fly algorithm is proposed, and the selection of the objective function is improved at the same time. The method first uses the fruit fly algorithm (FOA) to search for the global optimal combination of the VMDdecomposition parameter penalty factor and the number of decompositions, selects the information entropy increment and the kurtosis index as the objective function, obtains the optimal parameter combination, and then conducts the signal analysis. AfterVMDprocessing, several eigenmode components are obtained, and the optimal component is subjected to envelope analysis. In order to reduce the interference of redundant components and noise, the 1.5-dimensional spectrum is used to further study the optimal component, thereby diagnosing the fault type of the bearing. The above method is verified by the measured fault signal. The results show that the method can effectively extract the frequency characteristics of the fault signal, which proves that the method has certain accuracy and research value.